{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1907.04502","title":"DeepXDE: A deep learning library for solving differential equations","created":"2019-07-10","cited_by_count":619},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"2309.00583","title":"Geometry-Informed Neural Operator for Large-Scale 3D PDEs","created":"2023-09-01","cited_by_count":303},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2405.19101","title":"Poseidon: Efficient Foundation Models for PDEs","created":"2024-05-29","cited_by_count":200},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2403.03542","title":"DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training","created":"2024-03-06","cited_by_count":151},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2306.00258","title":"Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior","created":"2023-06-01","cited_by_count":131},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"2304.07993","title":"In-Context Operator Learning with Data Prompts for Differential Equation Problems","created":"2023-04-17","cited_by_count":101},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"id":"2204.09810","title":"Deep transfer operator learning for partial differential equations under conditional shift","created":"2022-04-20","cited_by_count":83},{"id":"2202.07643","title":"Lie Point Symmetry Data Augmentation for Neural PDE Solvers","created":"2022-02-15","cited_by_count":77},{"id":"2403.12553","title":"Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs","created":"2024-03-19","cited_by_count":59},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57},{"id":"2202.01889","title":"Generalizing to New Physical Systems via Context-Informed Dynamics Model","created":"2022-02-01","cited_by_count":50},{"id":"2303.11739","title":"Data-efficient Large Scale Place Recognition with Graded Similarity Supervision","created":"2023-03-21","cited_by_count":43},{"id":"2106.04546","title":"LEADS: Learning Dynamical Systems that Generalize Across Environments","created":"2021-06-08","cited_by_count":40},{"id":"2202.09346","title":"Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast","created":"2022-02-18","cited_by_count":37},{"id":"2402.15734","title":"Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning","created":"2024-02-24","cited_by_count":32},{"id":"2307.05432","title":"Self-Supervised Learning with Lie Symmetries for Partial Differential Equations","created":"2023-07-11","cited_by_count":29},{"id":"2210.14188","title":"MOFormer: Self-Supervised Transformer model for Metal-Organic Framework Property Prediction","created":"2022-10-25","cited_by_count":28},{"id":"2305.08757","title":"Physics Informed Token Transformer for Solving Partial Differential Equations","created":"2023-05-15","cited_by_count":21},{"id":"2309.16816","title":"PROSE: Predicting Operators and Symbolic Expressions using Multimodal Transformers","created":"2023-09-28","cited_by_count":16},{"id":"2311.14361","title":"Deciphering and integrating invariants for neural operator learning with various physical mechanisms","created":"2023-11-24","cited_by_count":15},{"id":"2403.17728","title":"Masked Autoencoders are PDE Learners","created":"2024-03-26","cited_by_count":14},{"id":"2310.18885","title":"A foundational neural operator that continuously learns without forgetting","created":"2023-10-29","cited_by_count":11},{"id":"2401.16327","title":"PICL: Physics Informed Contrastive Learning for Partial Differential Equations","created":"2024-01-29","cited_by_count":5},{"id":"2405.17509","title":"Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations","created":"2024-05-27","cited_by_count":5},{"id":"2312.02380","title":"FaultFormer: Pretraining Transformers for Adaptable Bearing Fault Classification","created":"2023-12-04","cited_by_count":3}],"next_cursor":null}